CN115320630A

CN115320630A - Automatic driving system, automatic driving control method, and non-transitory recording medium

Info

Publication number: CN115320630A
Application number: CN202210464712.3A
Authority: CN
Inventors: 岩本贵之; 佐藤国仁; 后藤健文
Original assignee: Toyota Motor Corp
Current assignee: Toyota Motor Corp
Priority date: 2021-05-11
Filing date: 2022-04-25
Publication date: 2022-11-11
Also published as: US20220363291A1; JP2022174596A; EP4089499A1

Abstract

The invention relates to an automatic driving system, an automatic driving control method and a non-transitory recording medium. The automatic driving system includes: one or more storage devices configured to store specific location information indicative of specific locations that may require remote support; and a processor configured to: determining whether there is an abnormality of a remote support system configured to provide the remote support to an autonomous vehicle; setting, as a limit position, an arbitrary specific position on a target route from a current position of the autonomous vehicle to a destination based on the specific position information when the abnormality of the remote support system is detected; setting a target retreat position so that the target retreat position is included in the target route from the current position to the limit position; and controlling the autonomous vehicle to stop at the target retreat position.

Description

Automatic driving system, automatic driving control method, and non-transitory recording medium

Technical Field

The present disclosure relates to an automatic driving system, an automatic driving control method, and a non-transitory recording medium.

The present application claims priority from japanese patent application 2021-080494, filed on 2021, 5, 11, which is hereby incorporated by reference in its entirety.

Background

Japanese patent laid-open No. 2018-077649 discloses a remote driving control apparatus that performs remote driving of a vehicle. The remote driving control device performs remote driving of the vehicle by communicating with the vehicle.

A remote support technology for remotely supporting the travel of an autonomous vehicle is considered. Remote support requires communication between the remote support device and the autonomous vehicle. The "remote support system" includes a configuration and a function for providing remote support to the autonomous vehicle. For example, the remote support system includes a remote support device, a communication network, a communication device mounted on an autonomous vehicle, and the like. When an abnormality occurs in at least a part of the remote support system, the remote support cannot be provided to the autonomous vehicle, or the accuracy of the remote support is reduced.

Disclosure of Invention

The present disclosure provides a technique capable of appropriately controlling an autonomous vehicle when an abnormality occurs in a remote support system that provides remote support for the autonomous vehicle.

A first aspect of the present disclosure is associated with an autonomous driving system configured to control an autonomous vehicle as a subject of remote support.

The automatic driving system includes: one or more storage devices configured to store specific location information indicative of specific locations that may require remote support; and one or more processors configured to: determining whether there is an abnormality of a remote support system configured to provide remote support for the autonomous vehicle; setting, as a limit position, an arbitrary specific position on a target route from a current position of the autonomous vehicle to a destination based on the specific position information when an abnormality of the remote support system is detected; setting a target retreat position so that the target retreat position is included in a target route from a current position to a limit position; and controlling the autonomous vehicle to stop at the target retreat position.

In the first aspect, the one or more processors may further obtain a first specific location on the target route that is closest to the current location based on the specific location information, and set the first specific location as the limit location.

In the first aspect, the one or more processors may further acquire a first specific position closest to the current position on the target route based on the specific position information, determine whether or not the first specific position satisfies an allowable condition, acquire a second specific position different from the first specific position on the target route based on the specific position information when the first specific position does not satisfy the allowable condition, and set the second specific position as the limit position. The permission condition may include at least one of (i) a distance between the current position and the first specific position being a distance threshold or more, and (ii) a vehicle control amount required when the autonomous vehicle is stopped in front of the first specific position being a control amount threshold or less.

In the first aspect described above, the one or more processors may further obtain a first specific location on the target route that is closest to the current location based on the specific location information, and set the first specific location as the limit location in a case where the abnormality of the remote support system is a functional failure.

In the first aspect, the one or more processors may further acquire a first specific location closest to the current location on the target route based on the specific location information, determine whether or not the first specific location satisfies a tolerance condition when the abnormality of the remote support system is performance degradation, acquire a second specific location different from the first specific location on the target route based on the specific location information when the first specific location does not satisfy the tolerance condition, and set the second specific location as the limit location. The permission condition may include at least one of (i) a distance between the current position and the first specific position being a distance threshold or more, and (ii) a vehicle control amount required when the autonomous vehicle is stopped in front of the first specific position being a control amount threshold or less.

A second aspect of the present disclosure is associated with an autonomous driving control method, executed by one or more processors, of controlling an autonomous driving vehicle as a subject of remote support.

The automatic driving control method comprises the following steps: determining whether there is an abnormality of a remote support system that provides remote support for the autonomous vehicle; setting, as a limit position, an arbitrary specific position on a target route from a current position of the autonomous vehicle to a destination based on the specific position information when an abnormality of the remote support system is detected; setting a target retreat position so that the target retreat position is included in a target route from a current position to a limit position; and controlling the autonomous vehicle to stop at the target retreat position. The specific location information indicates a specific location that may require remote support.

A third aspect of the present disclosure is associated with a non-transitory recording medium that stores a command executable by a computer and causes the computer to execute a function of controlling an autonomous vehicle that is an object of remote support.

The functions include: determining whether there is an abnormality of a remote support system that provides remote support for the autonomous vehicle; setting, as a limit position, an arbitrary specific position on a target route from a current position of the autonomous vehicle to a destination based on the specific position information when an abnormality of the remote support system is detected; setting a target retreat position so that the target retreat position is included in a target route from a current position to a limit position; and controlling the autonomous vehicle to stop at the target retreat position. The specific location information indicates a specific location that may require remote support.

According to aspects of the present disclosure, in the case where an abnormality of the remote support system is detected, the target backoff position is set in consideration of a specific position that may require remote support. Specifically, an arbitrary specific position on the target route to the destination is set as the limit position. The target retreat position is set to be included in a target route from the current position of the autonomous vehicle to the limit position.

The target retreat position does not need to be near the current position of the autonomous vehicle, but may be in front of the limit position. Therefore, the target retreat position can be set so that the autonomous vehicle can stop with a margin. According to the aspects of the present disclosure, the safety of the autonomous vehicle and surrounding vehicles can be improved.

Further, the automatic driving can be continued to the target retreat position without ending the automatic driving in the vicinity of the current position. According to the aspects of the present disclosure, the continuity of automatic driving can be improved.

Since an arbitrary specific position on the target route is set as the limit position, the number of specific positions through which the autonomous vehicle passes is reduced as compared with a case where the autonomous vehicle must travel to the destination. The probability of the need for remote support as a whole decreases as the number of specific locations through which the autonomous vehicle passes decreases. Thereby, the influence caused by an abnormality of the remote support system is at least reduced.

Drawings

Features, advantages and technical and industrial significance of exemplary embodiments of the present invention will be described below with reference to the accompanying drawings, wherein like reference numerals denote like elements, and wherein:

fig. 1 is a conceptual diagram of a remote support system representing an embodiment of the present disclosure.

Fig. 2 is a conceptual diagram for explaining an outline of remote support of the embodiment of the present disclosure.

Fig. 3 is a conceptual diagram for explaining an example of a specific position of the embodiment of the present disclosure.

Fig. 4 is a conceptual diagram for explaining an example of the backoff process according to the embodiment of the present disclosure.

Fig. 5 is a conceptual diagram for explaining an example of a parking candidate area according to the embodiment of the present disclosure.

Fig. 6 is a conceptual diagram for explaining an example of the high priority region and the low priority region in the embodiment of the present disclosure.

Fig. 7 is a conceptual diagram for explaining processing when an abnormality occurs in the remote support system according to the embodiment of the present disclosure.

Fig. 8 is a conceptual diagram for explaining an example of processing when an abnormality occurs in the remote support system according to the embodiment of the present disclosure.

Fig. 9 is a conceptual diagram for explaining another example of processing when an abnormality occurs in the remote support system according to the embodiment of the present disclosure.

Fig. 10 is a block diagram showing a configuration example of an automatic driving system according to an embodiment of the present disclosure.

Fig. 11 is a block diagram showing an example of driving environment information according to the embodiment of the present disclosure.

Fig. 12 is a flowchart showing an example of processing realized by the automatic driving system according to the embodiment of the present disclosure.

Fig. 13 is a flowchart showing a first example of step S300 according to the embodiment of the present disclosure.

Fig. 14 is a flowchart showing a second example of step S300 of the embodiment of the present disclosure.

Fig. 15 is a flowchart showing a third example of step S300 of the embodiment of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described with reference to the accompanying drawings.

1. Remote supported summary

Fig. 1 is a conceptual diagram illustrating a remote support system according to the present embodiment. The remote support system includes an autonomous vehicle 1, a remote support apparatus 2, and a communication network 3.

The autonomous vehicle 1 is an autonomous vehicle. As the automatic driving here, automatic driving (so-called automatic driving of level 3 or more) is assumed on the premise that the driver can not necessarily concentrate on driving 100%. The autonomous vehicle 1 may be an autonomous vehicle of class 4 or higher that does not require a driver. The autonomous vehicle 1 is a target of remote support in the present embodiment.

The remote support device 2 is a device for performing remote support of the autonomous vehicle 1, and is operated by a remote operator. The autonomous vehicle 1 and the remote support apparatus 2 are connected to be able to communicate with each other via a communication network 3. The remote support device 2 communicates with the autonomous vehicle 1 via the communication network 3, and remotely supports the traveling of the autonomous vehicle 1. More specifically, the remote operator operates the remote support device 2 to remotely support the travel of the autonomous vehicle 1. The remote support device 2 may be a device that assists the remote support of the autonomous vehicle 1 by the remote operator.

The communication network 3 includes a wireless base station, a wireless communication network, a wired communication network, and the like. An example of the wireless Communication network is a 5G (5 th Generation Mobile Communication Technology: fifth Generation Mobile Communication Technology) network.

Fig. 2 is a conceptual diagram for explaining an outline of remote support of the present embodiment. The autonomous driving system 10 controls the autonomous driving vehicle 1. In autonomous driving, the autonomous driving system 10 performs various vehicle processes. As a representative vehicle process in the automatic driving, the following processes can be cited.

(1) Identification processing: the automated driving system 10 uses the recognition sensor to recognize the condition of the periphery of the automated driving vehicle 1. For example, the autopilot system 10 uses a camera to identify the signal display of a signal light (e.g., green, yellow, red, right turn signal, etc.).

(2) And (4) action judgment processing: the automatic driving system 10 determines whether to perform an action based on the result of the recognition processing. Examples of the action include start, stop, right turn, left turn, lane change, and the like.

(3) And (3) timing judgment processing: the automatic driving system 10 determines the execution timing of the above-described action.

Typically, a situation in which remote support by a remote operator is required is a situation in which automatic driving is difficult. For example, at an intersection such as that shown in FIG. 3, remote support may be required.

For example, when sunlight is irradiated to a traffic light provided at an intersection, the recognition accuracy of the signal display may be degraded. In the case where the signal display cannot be accurately discriminated by the recognition processing, the automatic driving system 10 requires remote support for signal recognition. In addition, even when the signal display cannot be determined, it is difficult to determine at which timing which action should be performed. Thus, the automatic driving system 10 also requires remote support for the action determination process and the timing determination process.

It is also possible to consider a situation in which it is difficult to determine whether or not an action can be actually performed even if the signal display is determined. For example, after the signal viewed from the automatic driving system 10 indicates "right turn possible", the oncoming vehicle may enter the intersection, or the oncoming vehicle or the leading vehicle may be left behind in the intersection. In such a case, the automatic driving system 10 may request remote support for the action determination process and the timing determination process while being kept stopped.

As another example, a situation may be considered in which it is difficult to determine whether or not to perform a lane change when a construction section exists ahead of the autonomous vehicle 1. In this case, the autonomous driving system 10 may request remote support for the action determination process.

The automated driving system 10 may also request remote driving (remote operation) of the automated driving vehicle 1 from a remote operator. The "remote support" in the present embodiment refers to the following concept: the remote driving (remote operation) is included in addition to at least one of the support of the recognition processing, the action determination processing, and the timing determination processing.

When it is determined that the remote support is necessary, the automatic driving system 10 transmits a remote support request REQ to the remote support device 2 via the communication network 3. The remote support request REQ is information for requesting remote support of the autonomous vehicle 1 from the remote operator. The remote support apparatus 2 notifies the remote operator of the received remote support request REQ. In response to the remote support request REQ, the remote operator starts remote support of the autonomous vehicle 1.

In the remote support process, the automatic driving system 10 transmits vehicle information VCL to the remote support apparatus 2 via the communication network 3. The vehicle information VCL indicates the state of the autonomous vehicle 1, the surrounding situation, the result of vehicle processing performed by the autonomous system 10, and the like. The remote support apparatus 2 presents the vehicle information VCL received from the automatic driving system 10 to the remote operator. For example, as shown in fig. 2, the remote support apparatus 2 displays image information IMG captured by a camera mounted on the autonomous vehicle 1 on a display device.

The remote operator refers to the vehicle information VCL and performs remote support of the autonomous vehicle 1. The operator indication INS is an indication of the autonomous vehicle 1 input by a remote operator. The remote support apparatus 2 accepts an input of an operator instruction INS from a remote operator. Then, the remote support apparatus 2 transmits the operator instruction INS to the autonomous vehicle 1 via the communication network 3. The automated driving system 10 receives the operator instruction INS from the remote support apparatus 2, and controls the automated driving vehicle 1 in accordance with the received operator instruction INS.

2. Handling when an exception occurs for a remote support system

2-1. Remote support system exceptions

In the present embodiment, the "remote support system 4" refers to a configuration and a function for providing remote support to the autonomous vehicle 1. For example, the remote support system 4 includes a remote support device 2, a communication network 3, a communication device mounted on the autonomous vehicle 1, and the like (see fig. 1). Examples of the communication device mounted on the autonomous vehicle 1 include a communication ECU (Electronic Control Unit), a communication module, and a transmission/reception circuit.

In the following, a case is considered where "abnormality (abnormality)" occurs in at least a part of the remote support system 4 that provides remote support for the autonomous vehicle 1.

For example, the abnormality of the remote support system 4 includes "functional failure" in which the function of the remote support system 4 is lost. An example of a malfunction of the remote support system 4 is a communication interruption. For example, in a case where a problem (trouble) occurs in the communication network 3, communication interruption may occur. Another example of a malfunction of the remote support system 4 is a malfunction (shutdown) of the remote support apparatus 2.

A further example of a malfunction of the remote support system 4 is a failure of a communication device mounted on the autonomous vehicle 1. In the event of a functional failure of the remote support system 4, the autonomous vehicle 1 cannot be remotely supported.

The abnormality of the remote support system 4 may also include "performance degradation" in which the function of the remote support system 4 is degraded. One example of the performance degradation of the remote support system 4 is a significant degradation in communication speed, throughput (throughput). Another example of a performance degradation of the remote support system 4 is a significant increase in communication delay. Another example of the performance degradation of the remote support system 4 is a degradation of the internal communication speed and the calculation speed in the communication ECU mounted on the autonomous vehicle 1. When the performance of the remote support system 4 is degraded, the accuracy of the remote support may be degraded.

2-2. Backoff processing

When an abnormality occurs in the remote support system 4, the remote support cannot be provided to the autonomous vehicle 1 or the accuracy of the remote support is lowered. Therefore, in the case where an abnormality of the remote support system 4 is detected, the autonomous system 10 executes "retreat process" for safely retreating the autonomous vehicle 1.

Fig. 4 is a conceptual diagram for explaining an example of the backoff process according to the present embodiment. The "target retreat position PE" is a target stop position when the autonomous vehicle 1 is stopped by the retreat process. The target evacuation position PE may be set at a safe position on the road. In the example shown in fig. 4, the target retreat position PE is set at the shoulder. The automated driving system 10 controls the automated driving vehicle 1 to travel toward the target retreat position PE and stop at the target retreat position PE. For example, the automated driving system 10 generates a target trajectory TR along which the automated driving vehicle 1 travels from the current position toward the target retreat position PE and stops at the target retreat position PE. Then, the automated driving system 10 controls the running of the automated driving vehicle 1 in such a manner that the automated driving vehicle 1 follows the target trajectory TR.

An area that can be used as the target backoff position PE in the backoff process may be predetermined. Hereinafter, an area that can be used as the target evacuation position PE in the evacuation process is referred to as a "parking candidate area AC".

Fig. 5 is a conceptual diagram for explaining an example of the parking candidate area AC. To describe the parking candidate area AC, first, a "parking prohibited area AX" will be described. The parking prohibition area AX is an area where parking of the vehicle is prohibited, and is defined in advance by a road traffic law or the like. In the example shown in fig. 5, the parking prohibition area AX includes a crosswalk and a region of a predetermined width around the crosswalk. The parking prohibition area AX may include an area of a predetermined width at and around an intersection. In addition to this, the area in front of the fire fighting equipment, etc. are also included in the parking prohibition area AX.

The parking candidate area AC is selected from areas other than the parking prohibition area AX on the road. Typically, the parking candidate area AC is a part of an area other than the parking prohibition area AX. For example, the parking candidate area AC is selected from the viewpoint of safety assurance of the autonomous vehicle 1 after parking. As illustrated in fig. 5, the parking candidate area AC may be an area relatively close to the road end. The parking candidate area AC may be set to include a shoulder and a roadside band.

As shown in fig. 6, the priority may be set to the parking candidate area AC. The high priority area ACH is a parking candidate area AC with a higher priority, and the low priority area ACL is a parking candidate area AC with a lower priority. In the example shown in fig. 6, the straight line section is set to the high priority region ACH, and the curve section is set to the low priority region ACL.

The parking candidate area AC and the parking prohibited area AX are registered in the map information in advance, for example. In the evacuation process, the automatic driving system 10 may set the target evacuation position PE to be included in the parking candidate area AC. In the case where the priority is set to the parking candidate area AC, the automatic driving system 10 sets the target retreat position PE to be included in the parking candidate area AC having the highest priority as possible.

2-3. Back off margin interval

As described above, when an abnormality of the remote support system 4 is detected, the autonomous driving system 10 performs the back-off process. However, it is not necessarily required to bring the autonomous vehicle 1 to an emergency stop immediately after the abnormality of the remote support system 4 is detected. This is because the automated driving system 10 can continue the automated driving as usual in a situation where the remote support is not required. That is, although the abnormality of the remote support system 4 is detected, it is not necessary to take an urgent action to make an urgent lane change or an urgent deceleration. According to the present embodiment, the automatic driving system 10 also sets the target retreat position PE in consideration of the possibility that remote support is required.

Hereinafter, the position where the remote support for the autonomous vehicle 1 may be required is referred to as "specific position PS". For example, the specific position PS is an intersection as shown in fig. 3. As another example, the specific position PS may be a position other than an ODD (Operational Design area) that is an area where autonomous driving is possible. As another example, the specific position PS may include a construction section, a traffic jam section, an accident occurrence position, and the like. Typically, the specific position PS is registered in advance in the map information. Alternatively, information of the specific position PS such as the congestion section and the accident occurrence position may be acquired in real time.

Fig. 7 shows an example of the situation of automatic driving in which the abnormal timing of the remote support system 4 is detected. The current position and destination of the autonomous vehicle 1 are denoted by reference numerals "P1" and "DST", respectively. The target route RT from the current position P1 of the autonomous vehicle 1 to the destination DST is set by the autonomous system 10. The autonomous driving system 10 controls the autonomous vehicle 1 to travel to the destination DST along the target route RT.

At the point in time when an abnormality of the remote support system 4 is detected, a specific position PS exists on the target route RT to the destination DST. In the example shown in fig. 7, a plurality of specific positions PS1, PS2, PS3 exist on the target route RT. The automatic driving system 10 sets an arbitrary specific position PS on the target route RT to the "limit position PL". Hereinafter, the section of the target route RT from the current position P1 to the limit position PL is referred to as a "back-off margin section XE". The automatic driving system 10 selects the target evacuation position PE from the evacuation margin interval XE. That is, the automatic driving system 10 sets the target retreat position PE to be included in the retreat margin interval XE.

Fig. 8 is a conceptual diagram for explaining an example of the limit position PL and the backoff margin interval XE. In the example shown in fig. 8, the limit position PL is the first specific position PS1 closest to the current position P1 on the target route RT. The backoff margin interval XE is an interval from the current position P1 to the first specific position PS1. The target backoff position PE is selected from the backoff margin interval XE. The target retracted position PE need not be near the current position P1 but may be in front of the first specific position PS1 (limit position PL). Therefore, the target retreat position PE can be set so that the autonomous vehicle 1 can stop with a margin. In other words, the backoff process can be performed with a margin. This can improve the safety of the autonomous vehicle 1 and the surrounding vehicles.

In the example shown in fig. 8, the autonomous vehicle 1 does not stop at the target retreat position PE by passing through any specific position PS. Thus, a situation in which remote support is required does not occur. Thus, a situation in which remote support is required but remote support cannot be obtained can be avoided.

Fig. 9 is a conceptual diagram for explaining another example of the limit position PL and the backoff margin interval XE. The limit position PL is not limited to only the first specific position PS1 closest to the current position P1. For example, in the case where the current position P1 is immediately before the first specific position PS1, the second specific position PS2 following the first specific position PS1 may also be set as the limit position PL. The backoff margin interval XE is an interval from the current position P1 to the second specific position PS2. The target backoff position PE is selected from the backoff margin interval XE. This eliminates the need to make an extraordinary lane change or sudden deceleration for stopping the vehicle in front of the first specific position PS1. That is, the backoff processing can be performed with a margin.

In the example shown in fig. 9, the autonomous vehicle 1 needs to pass through the first specific position PS1. The first specific location PS1 is a location where remote support may be required, and remote support is not necessarily required at the first specific location PS1. If no remote support is required at the first specific position PS1, the autonomous vehicle 1 can pass through the first specific position PS1 by normal autonomous driving. Even if it is assumed that remote support is required at the first specific location PS1, if the abnormality of the remote support system 4 is "performance degradation", remote support can be performed although slow. In this case, the autonomous vehicle 1 can also pass through the first specific position PS1. After that, the autonomous vehicle 1 stops at the target retreat position PE before passing through the second specific position PS2. The number of specific positions PS through which the autonomous vehicle 1 passes is reduced compared to the case where the autonomous vehicle 1 must travel to the destination DST. The probability of the need for remote support as a whole drops, since the number of specific locations PS passed decreases. Thereby, the influence caused by an abnormality of the remote support system 4 is at least reduced.

2-4. Effect

As described above, according to the present embodiment, when an abnormality of the remote support system 4 is detected, the target backoff position PE is set in consideration of the specific position PS that may require remote support. Specifically, an arbitrary specific position PS on the target route RT to the destination DST is set as the limit position PL. The target evacuation position PE is set to be included in the target route RT (evacuation margin section XE) from the current position P1 of the autonomous vehicle 1 to the limit position PL.

The target retreat position PE does not necessarily need to be near the current position P1 but just before the limit position PL. Therefore, the target retreat position PE can be set so that the autonomous vehicle 1 can stop with a margin. In other words, the backoff process can be performed with a margin. This can improve the safety of the autonomous vehicle 1 and the surrounding vehicles.

Further, the automatic driving does not need to be terminated near the current position P1, and the automatic driving can be continued to the target retreat position PE. This improves the continuity of automatic driving.

Since the arbitrary specific position PS on the target route RT is set as the limit position PL, the number of specific positions PS through which the autonomous vehicle 1 passes is reduced as compared with a case where the autonomous vehicle 1 must travel to the destination DST. Since the number of specific positions PS through which the autonomous vehicle 1 passes is reduced, the probability of requiring remote support as a whole decreases. Thereby, the influence caused by an abnormality of the remote support system 4 is at least reduced.

The first specific position PS1 closest to the current position P1 on the target route RT may also be set as the limit position PL. In this case, the autonomous vehicle 1 stops at the target retracted position PE without passing through any specific position PS. Thus, a situation in which remote support is required does not occur. Thus, a situation in which remote support is required but remote support cannot be obtained can be avoided.

The automatic driving system 10 according to the present embodiment will be described in further detail below.

3. Examples of automatic Driving systems

3-1. Example of construction

The autonomous driving system 10 controls the autonomous driving vehicle 1. Typically, the autonomous driving system 10 is mounted on the autonomous vehicle 1. Alternatively, at least a part of the autonomous system 10 may be disposed in an external device outside the autonomous vehicle 1, and may remotely control the autonomous vehicle 1. That is, the autonomous system 10 may be disposed in the autonomous vehicle 1 and the external device in a distributed manner.

Fig. 10 is a block diagram showing an example of the configuration of the automatic driving system 10 according to the present embodiment. The autopilot system 10 includes a sensor group 20, a travel device 30, a communication device 40, and a control device 100.

The sensor group 20 is mounted on the autonomous vehicle 1. The sensor group 20 includes a vehicle state sensor, an identification sensor, a position sensor, and the like. The vehicle state sensor detects the state of the autonomous vehicle 1. Examples of the vehicle state sensor include a vehicle speed sensor, a yaw rate sensor, a lateral acceleration sensor, a steering angle sensor, and the like. The recognition sensor detects the condition around the autonomous vehicle 1. Examples of the recognition sensor include a camera, a Laser Imaging Detection and Ranging (LIDAR), and a radar. The position sensor detects the position and orientation of the autonomous vehicle 1. An example of the position sensor is a GPS (Global Positioning System) sensor.

Running device 30 is mounted on autonomous vehicle 1. The running device 30 includes a steering device, a driving device, and a braking device. The steering device steers the wheels. The Steering device includes, for example, a Power Steering (EPS) device. The driving device is a power source that generates driving force. Examples of the driving device include an engine, an electric motor, and an in-wheel motor. The brake device generates a braking force.

The communication device 40 communicates with the outside of the autonomous vehicle 1. For example, the communication device 40 communicates with the remote support apparatus 2 via the communication network 3 (see fig. 1 and 2). The communication device 40 may also communicate with the management server. The communication device 40 may also perform V2I (vehicle-to-vehicle) communication with the surrounding infrastructure. The communication device 40 may perform V2V (vehicle-to-vehicle) communication with the nearby vehicle. The communication device 40 includes a communication ECU (Electronic Control Unit), a communication module, a transmission/reception circuit, and the like.

The control device 100 controls the autonomous vehicle 1. The control device 100 includes one or more processors 110 (hereinafter, referred to as only the processors 110) and one or more storage devices 120 (hereinafter, referred to as only the storage devices 120). The processor 110 performs various processes. For example, processor 110 includes a CPU (Central Processing Unit). The storage device 120 stores various information. Examples of the storage device 120 include a volatile memory, a nonvolatile memory, an HDD (Hard Disk Drive), an SSD (Solid State Drive), and the like. The control device 100 may also include one or more ECUs. A part of the control device 100 may be an information processing device outside the autonomous vehicle 1.

The automated driving control program PROG is a computer program for controlling the automated driving vehicle 1. Various processes performed by the control device 100 are realized by the processor 110 executing the automatic driving control program PROG. The automatic driving control program PROG is stored in the storage device 120. Alternatively, the automatic driving control program PROG may be recorded in a computer-readable recording medium.

3-2. Driving environment information

The driving environment information 200 represents the driving environment of the autonomous vehicle 1. The driving environment information 200 is stored in the storage device 120.

Fig. 11 is a block diagram showing an example of driving environment information 200. The driving environment information 200 includes map information 210, specific position information 220, evacuation area information 230, vehicle state information 240, surrounding situation information 250, vehicle position information 260, and distribution information 270.

The map information 210 includes a general navigation map. The map information 210 may also indicate lane arrangement, road shape, and the like. The map information 210 may also include location information such as signals, signs, and the like. The processor 110 obtains map information for a desired area from a map database. The map database may be stored in a predetermined storage device mounted on the autonomous vehicle 1, or may be stored in an external management server. In the latter case, the processor 110 communicates with the management server to acquire the required map information.

The specific location information 220 represents a specific location PS where remote support of the autonomous vehicle 1 may be required. For example, the specific location information 220 is prepared in advance. Specific location information 220 may also be included in the map information 210. The specific location information 220 may be added in real time as described later.

The evacuation area information 230 indicates the positions of the parking candidate area AC and the parking prohibition area AX (see fig. 5). The evacuation area information 230 may indicate the priority of the parking candidate area AC (see fig. 6). The backoff area information 230 is created in advance. The backoff area information 230 may also be included in the map information 210.

The vehicle state information 240 is information indicating the state of the autonomous vehicle 1. The processor 110 obtains vehicle state information 240 from the vehicle state sensors.

The surrounding situation information 250 is information indicating the situation around the autonomous vehicle 1. The processor 110 acquires the surrounding situation information 250 using the recognition sensor. For example, the surrounding situation information 250 includes image information IMG captured by a camera. The surrounding situation information 250 also includes object information relating to objects around the autonomous vehicle 1. Examples of the object include a pedestrian, a bicycle, another vehicle (a preceding vehicle, a parked vehicle, or the like), a road structure (a white line, a curb, a guardrail, a wall, a center barrier, a roadside structure, or the like), a sign, an obstacle, and the like. The object information indicates the relative position and the relative speed of the object with respect to the autonomous vehicle 1.

The vehicle position information 260 is information indicating the position of the autonomous vehicle 1. The processor 110 acquires the vehicle position information 260 from the detection result obtained by the position sensor. The processor 110 may acquire the highly accurate vehicle position information 260 by a well-known self-position estimation process (Localization) using the object information and the map information 210.

The distribution information 270 includes road traffic information, construction section information, traffic control information, and the like. Processor 110 receives distribution information 270 from an information providing server or roadside infrastructure via communication device 40.

The processor 110 can grasp a construction section, a congestion section, an accident occurrence position, and the like based on the distribution information 270. In this case, the processor 110 may add a construction section, a traffic jam section, an accident occurrence position, and the like to the specific position information 220.

3-3. Vehicle running control and automatic driving control

The processor 110 executes "vehicle travel control" that controls travel of the autonomous vehicle 1. The vehicle running control includes steering control, acceleration control, and deceleration control. The processor 110 executes vehicle travel control by controlling the travel device 30 (steering device, driving device, braking device). Specifically, the processor 110 performs steering control by controlling the steering device. Further, the processor 110 performs acceleration control by controlling the driving device. Further, the processor 110 performs deceleration control by controlling the braking device.

Further, the processor 110 performs automatic driving control based on the driving environment information 200. More specifically, the processor 110 sets the target route RT to the destination DST based on the map information 210 and the like. The processor 110 performs vehicle travel control so that the autonomous vehicle 1 travels to the destination DST along the target route RT based on the driving environment information 200.

In more detail, the processor 110 generates a travel plan of the autonomous vehicle 1 based on the driving environment information 200. The travel plan includes maintaining a current travel lane, performing a lane change, avoiding an obstacle, and the like. Further, the processor 110 generates a target trajectory TR required for the autonomous vehicle 1 to travel according to the travel plan. The target trajectory TR includes a target position and a target speed. Then, the processor 110 executes vehicle travel control in such a manner that the autonomous vehicle 1 follows the target route RT and the target trajectory TR.

3-4. Processing associated with remote support

During autopilot, processor 110 determines whether remote support by a remote operator is required. Typically, a situation in which remote support by a remote operator is required is a situation in which automatic driving is difficult. For example, when it is difficult to perform at least one of the above-described recognition processing, action determination processing, and timing determination processing, the processor 110 determines that remote support by a remote operator is necessary.

In a case where it is determined that the remote support is required, the processor 110 transmits the remote support request REQ to the remote support apparatus 2 via the communication device 40. The remote support request REQ requests the remote operator to request the remote support of the autonomous vehicle 1.

Further, the processor 110 transmits the vehicle information VCL to the remote support apparatus 2 via the communication apparatus 40. The vehicle information VCL includes at least a part of the driving environment information 200. The vehicle information VCL includes, for example, image information IMG captured by a camera. The vehicle information VCL may also include object information. The vehicle information VCL may also include vehicle status information 240, vehicle location information 260. The vehicle information VCL may also include the results of the recognition processing, the action determination processing, and the timing determination processing.

Also, the processor 110 receives an operator indication INS from the remote support apparatus 2 via the communication apparatus 40. The operator indication INS is an indication of the autonomous vehicle 1 input by a remote operator. Upon receiving the operator instruction INS, the processor 110 performs vehicle travel control in accordance with the received operator instruction INS.

4. Processing flow when exception of remote support system occurs

Fig. 12 is a flowchart showing an example of processing performed by the automatic driving system 10 according to the present embodiment. In particular, fig. 12 shows a process flow associated with the occurrence of an exception of the remote support system 4.

4-1. Step S100

In step S100, the processor 110 determines whether or not there is an abnormality of the remote support system 4 that provides remote support for the autonomous vehicle 1. For example, the remote support system 4 includes the remote support apparatus 2, the communication network 3, and the communication apparatus 40 of the automatic driving system 10.

The anomaly of remote support system 4 includes a "malfunction" in which the function of remote support system 4 is lost. For example, processor 110 monitors communication conditions (e.g., throughput, communication speed) with remote support apparatus 2. When the communication with the remote support apparatus 2 is interrupted, the processor 110 determines that a functional failure has occurred in the remote support apparatus 2 or the communication network 3. As another example, the communication device 40 (e.g., communication ECU) of the automated driving system 10 has a self-diagnosis function. Processor 110 is able to detect a malfunction of communication device 40 through the self-diagnostic function.

The abnormality of the remote support system 4 may also include a performance degradation in which the function of the remote support system 4 is degraded. For example, processor 110 monitors communication conditions (e.g., throughput, communication speed, communication delay) with remote support apparatus 2. In the case where the throughput or the communication speed is lower than the first threshold value, the processor 110 determines that the performance degradation of the remote support system 4 has occurred. As another example, in the case where the communication delay exceeds the second threshold, the processor 110 determines that the performance degradation of the remote support system 4 has occurred.

If the abnormality of the remote support system 4 is not detected (no in step S100), the process in the present loop is ended. On the other hand, when an abnormality of the remote support system 4 is detected (step S100: YES), the process proceeds to step S200.

4-2. Step S200

In step S200, the processor 110 determines whether or not the specific position PS exists on the target route RT from the current position P1 to the destination DST. The target route RT is set and grasped by the processor 110. The specific position PS is obtained from the specific position information 220. Thus, the processor 110 can determine whether the specific location PS exists on the target route RT based on the specific location information 220.

In the case where the specific position PS exists on the target route RT (yes in step S200), the process proceeds to step S300. On the other hand, in the case where the specific position PS does not exist on the target route RT (step S200: NO), the process proceeds to step S400.

4-3. Step S300

In step S300, the processor 110 sets an arbitrary specific position PS on the target route RT as the limit position PL based on the target route RT and the specific position information 220. After that, the process advances to step S500. Several examples of step S300 will be described below.

4-3-1. First example

Fig. 13 is a flowchart showing a first example of step S300.

In step S310, the processor 110 acquires a first specific position PS1 closest to the current position P1 on the target route RT. The current position P1 is obtained from the vehicle position information 260. The specific position PS is obtained from the specific position information 220. The processor 110 can obtain the first specific position PS1 based on the specific position information 220 and the vehicle position information 260.

In step S340, the processor 110 sets the first specific position PS1 as the limit position PL.

According to the first example, the autonomous vehicle 1 can be stopped without passing through any specific position PS.

4-3-2. Second example

Fig. 14 is a flowchart showing a second example of step S300. Step S310 is the same as in the first example.

In step S330, the processor 110 determines whether the first specific position PS1 satisfies the allowance condition. The permission condition is set from the viewpoint of whether or not the autonomous vehicle 1 can be stopped without a difficult lane change or sudden deceleration.

For example, the allowable conditions include at least one of the following conditions (a) and (B).

Condition (a): the distance between the current position P1 and the first specific position PS1 is equal to or greater than a predetermined distance threshold.

Condition (B): the vehicle control amount required when the autonomous vehicle 1 is stopped in front of the first specific position PS1 is equal to or less than the control amount threshold value. Here, the deceleration and the steering amount are shown as examples of the vehicle control amount.

The current position P1 of the autonomous vehicle 1 is obtained from the vehicle position information 260. The current vehicle speed of the autonomous vehicle 1 is obtained from the vehicle state information 240. The motion performance of the autonomous vehicle 1 is given as information in advance. The processor 110 determines whether the first specific position PS1 satisfies the allowable condition based on the current position P1, the first specific position PS1, the current vehicle speed, the motion performance, and the like.

When the first specific position PS1 satisfies the permission condition (yes in step S330), the process proceeds to step S340. In step S340, the processor 110 sets the first specific position PS1 as the limit position PL.

On the other hand, when the first specific position PS1 does not satisfy the permission condition (NO in step S330), the process proceeds to step S350. In step S350, the processor 110 acquires a second specific location PS2 different from the first specific location PS1 on the target route RT based on the specific location information 220. For example, the second specific position PS2 is a specific position PS (see fig. 9) subsequent to the first specific position PS1 when viewed from the current position P1. After that, the process advances to step S360.

In step S360, the processor 110 sets the second specific position PS2 as the limit position PL.

According to the second example, the autonomous vehicle 1 can be stopped without performing an unnecessary lane change or sudden deceleration.

4-3-3. Third example

Fig. 15 is a flowchart showing a third example of step S300. Step S310 is the same as in the first example.

In step S320, the processor 110 determines whether the abnormality of the remote support system 4 is a functional failure or performance degradation.

In the case where the abnormality of the remote support system 4 is a functional failure (yes in step S320), the process proceeds to step S340. In step S340, the processor 110 sets the first specific position PS1 as the limit position PL.

On the other hand, if the abnormality of the remote support system 4 is a performance degradation (no in step S320), the process proceeds to step S330. Step S330 is the same as the second example.

According to the third example, when the abnormality of the remote support system 4 is a performance degradation, the selection range of the target backoff position PE can be expanded. That is, in the case where the abnormality of the remote support system 4 is a performance degradation, the condition imposed on the target backoff position PE can be relaxed.

4-4. Step S400

In step S400, the processor 110 sets the destination DST to the limit position PL. After that, the process advances to step S500.

4-5. Step S500

In step S500, the processor 110 sets the target retreat position PE based on the limit position PL. Specifically, the processor 110 acquires a section of the target route RT from the current position P1 to the limit position PL as the back-off margin section XE. Then, the processor 110 selects a target backoff position PE from the backoff margin interval XE. That is, the processor 110 sets the target backoff position PE to be included in the backoff margin interval XE.

The processor 110 sets the target retreat position PE so that the autonomous vehicle 1 can actually stop based on the current position P1 of the autonomous vehicle 1, the vehicle speed, the motion performance, and the like.

The processor 110 may also refer to the backoff area information 230 when setting the target backoff position PE. The evacuation area information 230 shows the positions of the parking candidate area AC and the parking prohibition area AX. The processor 110 sets the target retraction position PE in the parking candidate area AC included in the retraction margin interval XE, avoiding the parking prohibition area AX. The evacuation area information 230 may also show the priority of the parking candidate area AC. In this case, the processor 110 sets the target retreat position PE to be included in the parking candidate area AC having the highest priority as possible.

4-6. Step S600

In step S600, the processor 110 performs vehicle travel control such that the autonomous vehicle 1 travels toward the target retracted position PE and stops at the target retracted position PE. For example, the processor 110 generates a target trajectory TR such that the autonomous vehicle 1 travels from the current position P1 to the target evacuation position PE and stops at the target evacuation position PE. Then, the automated driving system 10 performs vehicle travel control so that the automated driving vehicle 1 follows the target trajectory TR (see fig. 4).

Claims

1. An autonomous driving system configured to control an autonomous vehicle as an object of remote support, the autonomous driving system characterized by comprising:

one or more storage devices configured to store specific location information indicative of specific locations where the remote support may be needed; and

one or more processors for executing a program to perform,

the one or more processors are configured to:

determining whether there is an abnormality of a remote support system configured to provide the remote support to the autonomous vehicle;

setting, when the abnormality of the remote support system is detected, an arbitrary specific position on a target route from a current position of the autonomous vehicle to a destination as a limit position based on the specific position information;

setting a target retreat position so that the target retreat position is included in the target route from the current position to the limit position; and

controlling the autonomous vehicle to stop at the target retreat position.

2. The autopilot system of claim 1,

the one or more processors are further configured to:

acquiring a first specific position closest to the current position on the target route based on the specific position information; and

setting the first specific position as the limit position.

3. The autopilot system of claim 1,

the one or more processors are further configured to:

acquiring a first specific location closest to the current location on the target route based on the specific location information;

determining whether the first specific position satisfies an allowable condition, wherein the allowable condition includes at least one of the following (i) and (ii): (i) A distance between the current position and the first specific position is equal to or greater than a distance threshold, (ii) a vehicle control amount required when the autonomous vehicle is stopped in front of the first specific position is equal to or less than a control amount threshold;

acquiring a second specific position different from the first specific position on the target route based on the specific position information in a case where the first specific position does not satisfy the permission condition; and

setting the second specific position as the limit position.

4. The autopilot system of claim 1,

the one or more processors are further configured to:

setting the first specific position to the limit position in the case where the abnormality of the remote support system is a functional failure.

5. The autopilot system of claim 1,

the one or more processors are further configured to:

in a case where the abnormality of the remote support system is a performance decline, determining whether or not the first specific location satisfies a tolerance condition, wherein the tolerance condition includes at least one of the following (i) and (ii): (i) A distance between the current position and the first specific position is equal to or greater than a distance threshold, (ii) a vehicle control amount required when the autonomous vehicle is stopped in front of the first specific position is equal to or less than a control amount threshold;

setting the second specific position as the limit position.

6. An autonomous driving control method, executed by one or more processors, of controlling an autonomous vehicle as a target of remote support, the autonomous driving control method characterized by comprising:

determining whether there is an abnormality of a remote support system that provides the remote support to the autonomous vehicle;

setting, as a limit position, an arbitrary specific position on a target route from a current position of the autonomous vehicle to a destination based on specific position information indicating the specific position where the remote support may be required, when the abnormality of the remote support system is detected;

controlling the autonomous vehicle to stop at the target retreat position.

7. A non-transitory recording medium storing a command executable by a computer and causing the computer to execute the following functions of controlling an autonomous vehicle as a target of remote support:

setting, when the abnormality of the remote support system is detected, an arbitrary specific location on a target route from a current location of the autonomous vehicle to a destination as a limit location based on specific location information indicating the specific location where the remote support may be required;

controlling the autonomous vehicle to stop at the target retreat position.